vpcom's picture
Training in progress, step 100
a6c5a27
raw
history blame
791 Bytes
{
"activation_function": "gelu_new",
"architectures": [
"SymbolicGPTLMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 0,
"embd_pdrop": 0.1,
"eos_token_id": 2,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 512,
"n_head": 8,
"n_inner": null,
"n_layer": 8,
"n_points": 30,
"n_positions": 256,
"n_vars": 1,
"n_ys": 1,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 284
}